Analytics answers three questions about your Agent: is it running, is it working, and what is it costing?
Go to Agent → open an Agent → Monitor → Analytics.
What do the charts show?
The page has six sections. Use the tabs at the top to move between them, and the controls beside the heading to change the dates. Filter narrows every chart to a trigger, a version, or a model.
| Section | What's in it |
|---|---|
| Runs | How many runs, how they ended, which model they asked for, how long they took, and how often they failed |
| Model calls | Every time the Agent asked a model something, and how long it waited |
| Cost & tokens | Credits per run, total usage, and where your spend is going |
| Tools | How often each tool was used, how slow it was, and how often it failed |
| Step types | What the Agent's steps were made up of |
| Scores | How your Agent is scoring on real runs, and how many were graded |
Runs you stopped yourself, and runs stopped by a limit, don't count as failures, but they're still part of the total the failure rate is measured against. Timings only count runs that finished.
How do I share what I'm looking at?
Copy the address from your browser and send it. The dates, the grouping, and any filters you picked are part of the link, so a teammate who opens it sees the same view. This works on one Agent's Analytics and on the page that compares all your Agents.
How do I compare all my Agents?
Go to Agent → Analytics in the sidebar. It ranks every Agent in your Organization over the dates you pick:
- Totals for spend, runs, active Agents, error rate, and duration
- A table of every Agent, sorted by spend by default. Sort by any column, and click an Agent to open its own Analytics over the same dates
- Spend and runs over time for your busiest Agents, with the rest grouped as Other agents
- Runs by trigger, spend by source and by model, and the tools your Agents call most
Spend here includes Auto-improve, scoring, and run summaries, so an Agent that rarely runs can still rank high. Deleted Agents are grouped in one row at the bottom, since their spend still counts.
Why is my spend higher than the runs chart suggests?
Because runs aren't the only thing that costs credits. Spend by source, under the Cost charts, splits your spend into runs and everything else: Auto-improve, scoring real runs, and run summaries.
The other charts only count runs, so this is where the rest shows up.
How do I bring costs down?
- Cap a single run under Manage → Agent settings → Run limits
- Drop the model tier if the Agent's job doesn't need the top one
- Remove tools the Agent doesn't use
- Grade fewer real runs, or turn that off completely
- Put a credit limit on Auto-improve
See Costs and limits.
Additional FAQ
What counts as a failed run?
A run that finished and failed. Runs you stopped yourself, and runs stopped by a limit, aren't counted as failures, though they're still in the total the rate is measured against. Only runs that never reached a known ending are left out altogether.
Where do I see credits for my whole Organization?
On the AI Credits page. Agent → Analytics covers what your Agents spent; AI Credits also covers apps and chat.
My Agent is slow. What do I check?
Open a slow run in Run history and read back through its steps. You'll see whether the time went on the model or on one of the tools, and the Tools section here shows which tool is slow across every run.
The Scores section is empty
Nothing has graded a real run yet. Turn on grading for a scorer that doesn't need an expected answer.